DeepSeek OCR QVLM 4 bit (SafeTensors) This is a 4 bit quantized version of deepseek ai/DeepSeek OCR using QVLM (Quantized Vision Language Model) technique, saved in SafeTensors format for easy deployment. 📊 Model Statistics Metric Value Original Size 6363.12 MB (6.21 GB) Quantized Size 2199.39 MB (2.15 GB) Size Reduction 4165.03 MB (65.46%) Compression Ratio 2.89x Format SafeTensors 🔧 Quantization Details Method: QVLM 4 bit group wise quantization Quantization Bits: 4 Group Size: 128 Vision Encoder: Quantized Language Model: Quantized Symmetric: False Parameters Quantized: 2,973,512,704 / 3,336,106,240 (89.13%) 🚀 Usage Basic Loading With Dequantization 📁 Model Files model.safetensors Quantized weights in SafeTensors format (2199.39 MB) config.json Model configuration with quantization settings quantization config.json Detailed quantization configuration quantization results.json Compression statistics tokenizer.json Tokenizer vocabulary tokenizer config.json Tokenizer configuration 🎯 Performance The quantized model achieves 2.9x compression while maintaining similar accuracy to the original model. The 4 bit quantization significantly reduces memory requirements, making it suit…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy